Re: [PATCH v3] ceph: invalidate pages when doing direct/sync writes

From: Xiubo Li
Date: Thu Apr 07 2022 - 10:49:17 EST

On 4/7/22 10:38 PM, Luís Henriques wrote:
When doing a direct/sync write, we need to invalidate the page cache in
the range being written to. If we don't do this, the cache will include
invalid data as we just did a write that avoided the page cache.

Signed-off-by: Luís Henriques <lhenriques@xxxxxxx>
fs/ceph/file.c | 9 +++++++++
1 file changed, 9 insertions(+)

Ok, here's a new attempt. After discussion in this thread and on IRC, I
think this is the right fix. generic/647 now passes with and without
encryption. Thanks!

Changes since v2:
- Invalidation needs to be done after a write

Changes since v1:
- Replaced truncate_inode_pages_range() by invalidate_inode_pages2_range
- Call fscache_invalidate with FSCACHE_INVAL_DIO_WRITE if we're doing DIO

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 5072570c2203..63e67eb60310 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1938,6 +1938,15 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
+ ret = invalidate_inode_pages2_range(
+ inode->i_mapping,
+ pos >> PAGE_SHIFT,
+ (pos + len - 1) >> PAGE_SHIFT);
+ if (ret < 0) {
+ dout("invalidate_inode_pages2_range returned %d\n",
+ ret);
+ ret = 0;
+ }
pos += len;
written += len;
dout("sync_write written %d\n", written);


Maybe it worth adding a comment to explain why we need this and where the mapping come from ?

Reviewed-by: Xiubo Li <xiubli@xxxxxxxxxx>